University of Hertfordshire

From the same journal

By the same authors

Intelligent Health Monitoring of Machine Bearings Based on Feature Extraction

Research output: Contribution to journalArticlepeer-review

Standard

Intelligent Health Monitoring of Machine Bearings Based on Feature Extraction. / Chalouli, Mohammed; Berrached, Nasr-eddine; Denai, Mouloud.

In: Journal of Failure Analysis and Prevention, Vol. 17, No. 5, 01.10.2017, p. 1053-1066.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Chalouli, Mohammed ; Berrached, Nasr-eddine ; Denai, Mouloud. / Intelligent Health Monitoring of Machine Bearings Based on Feature Extraction. In: Journal of Failure Analysis and Prevention. 2017 ; Vol. 17, No. 5. pp. 1053-1066.

Bibtex

@article{8e5cba8671cb4e839607b466f280a435,
title = "Intelligent Health Monitoring of Machine Bearings Based on Feature Extraction",
abstract = "Finding reliable condition monitoring solutions for large-scale complex systems is currently a major challenge in industrial research. Since fault diagnosis is directly related to the features of a system, there have been many research studies aimed to develop methods for the selection of the relevant features. Moreover, there are no universal features for a particular application domain such as machine diagnosis. For example, in machine bearing fault diagnosis, these features are often selected by an expert or based on previous experience. Thus, for each bearing machine type, the relevant features must be selected. This paper attempts to solve the problem of relevant features identification by building an automatic fault diagnosis process based on relevant feature selection using a data-driven approach. The proposed approach starts with the extraction of the time-domain features from the input signals. Then, a feature reduction algorithm based on cross-correlation filter is applied to reduce the time and cost of the processing. Unsupervised learning mechanism using K-means++ selects the relevant fault features based on the squared Euclidian distance between different health states. Finally, the selected features are used as inputs to a self-organizing map producing our health indicator. The proposed method is tested on roller bearing benchmark datasets.",
keywords = "Failure diagnosis; Bearing faults; Time-domain features; Condition-based maintenance; Health indicators; Relevant features; Fault feature extraction ",
author = "Mohammed Chalouli and Nasr-eddine Berrached and Mouloud Denai",
note = "This document is the Accepted Manuscript of the following article: Mohammed Chalouli, Nasr-eddine Berrached, and Mouloud Denai, {\textquoteleft}Intelligent Health Monitoring of Machine Bearings Based on Feature Extraction{\textquoteright}, Journal of Failure Analysis and Prevention, Vol. 17 (5): 1053-1066, October 2017. Under embargo. Embargo end date: 31 August 2018. The final publication is available at Springer via DOI: https://doi.org/10.1007/s11668-017-0343-y. ",
year = "2017",
month = oct,
day = "1",
doi = "10.1007/s11668-017-0343-y",
language = "English",
volume = "17",
pages = "1053--1066",
journal = "Journal of Failure Analysis and Prevention",
issn = "1547-7029",
publisher = "Springer Verlag",
number = "5",

}

RIS

TY - JOUR

T1 - Intelligent Health Monitoring of Machine Bearings Based on Feature Extraction

AU - Chalouli, Mohammed

AU - Berrached, Nasr-eddine

AU - Denai, Mouloud

N1 - This document is the Accepted Manuscript of the following article: Mohammed Chalouli, Nasr-eddine Berrached, and Mouloud Denai, ‘Intelligent Health Monitoring of Machine Bearings Based on Feature Extraction’, Journal of Failure Analysis and Prevention, Vol. 17 (5): 1053-1066, October 2017. Under embargo. Embargo end date: 31 August 2018. The final publication is available at Springer via DOI: https://doi.org/10.1007/s11668-017-0343-y.

PY - 2017/10/1

Y1 - 2017/10/1

N2 - Finding reliable condition monitoring solutions for large-scale complex systems is currently a major challenge in industrial research. Since fault diagnosis is directly related to the features of a system, there have been many research studies aimed to develop methods for the selection of the relevant features. Moreover, there are no universal features for a particular application domain such as machine diagnosis. For example, in machine bearing fault diagnosis, these features are often selected by an expert or based on previous experience. Thus, for each bearing machine type, the relevant features must be selected. This paper attempts to solve the problem of relevant features identification by building an automatic fault diagnosis process based on relevant feature selection using a data-driven approach. The proposed approach starts with the extraction of the time-domain features from the input signals. Then, a feature reduction algorithm based on cross-correlation filter is applied to reduce the time and cost of the processing. Unsupervised learning mechanism using K-means++ selects the relevant fault features based on the squared Euclidian distance between different health states. Finally, the selected features are used as inputs to a self-organizing map producing our health indicator. The proposed method is tested on roller bearing benchmark datasets.

AB - Finding reliable condition monitoring solutions for large-scale complex systems is currently a major challenge in industrial research. Since fault diagnosis is directly related to the features of a system, there have been many research studies aimed to develop methods for the selection of the relevant features. Moreover, there are no universal features for a particular application domain such as machine diagnosis. For example, in machine bearing fault diagnosis, these features are often selected by an expert or based on previous experience. Thus, for each bearing machine type, the relevant features must be selected. This paper attempts to solve the problem of relevant features identification by building an automatic fault diagnosis process based on relevant feature selection using a data-driven approach. The proposed approach starts with the extraction of the time-domain features from the input signals. Then, a feature reduction algorithm based on cross-correlation filter is applied to reduce the time and cost of the processing. Unsupervised learning mechanism using K-means++ selects the relevant fault features based on the squared Euclidian distance between different health states. Finally, the selected features are used as inputs to a self-organizing map producing our health indicator. The proposed method is tested on roller bearing benchmark datasets.

KW - Failure diagnosis; Bearing faults; Time-domain features; Condition-based maintenance; Health indicators; Relevant features; Fault feature extraction

U2 - 10.1007/s11668-017-0343-y

DO - 10.1007/s11668-017-0343-y

M3 - Article

VL - 17

SP - 1053

EP - 1066

JO - Journal of Failure Analysis and Prevention

JF - Journal of Failure Analysis and Prevention

SN - 1547-7029

IS - 5

ER -